Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination

Fangyi Zhang, Jürgen Leitner, Michael Milford, Peter I. Corke

CVPRW 2017 pp. 496-497

doi:10.1109/CVPRW.2017.74 /cvprw/2017/zhang2017cvprw-tuning/

Abstract

This paper introduces an end-to-end fine-tuning method to improve hand-eye coordination in modular deep visuomotor policies (modular networks) where each module is trained independently. Benefiting from weighted losses, the fine-tuning method significantly improves the performance of the policies for a robotic planar reaching task.

PDF CVPRW Semantic Scholar

Cite

Text

Zhang et al. "Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.74

Markdown

[Zhang et al. "Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/zhang2017cvprw-tuning/) doi:10.1109/CVPRW.2017.74

BibTeX

@inproceedings{zhang2017cvprw-tuning,
  title     = {{Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination}},
  author    = {Zhang, Fangyi and Leitner, Jürgen and Milford, Michael and Corke, Peter I.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {496-497},
  doi       = {10.1109/CVPRW.2017.74},
  url       = {https://mlanthology.org/cvprw/2017/zhang2017cvprw-tuning/}
}